Cumincad : CUMINCAD Papers : Search Results

CumInCAD is a Cumulative Index about publications in Computer Aided Architectural Design
supported by the sibling associations ACADIA, CAADRIA, eCAADe, SIGraDi, ASCAAD and CAAD futures

PDF papers
References

Hits 1 to 20 of 17667

Reformat results as: short short into frame detailed detailed into frame

_id	ecaade2014_159
id	ecaade2014_159
authors	Leyla Yunis, Ond_ej Kyjánek, Moritz Dörstelmann, Marshall Prado, Tobias Schwinn and Achim Menges
year	2014
title	Bio-inspired and fabrication-informed design strategies for modular fibrous structures in architecture
doi	https://doi.org/10.52842/conf.ecaade.2014.1.423
source	Thompson, Emine Mine (ed.), Fusion - Proceedings of the 32nd eCAADe Conference - Volume 1, Department of Architecture and Built Environment, Faculty of Engineering and Environment, Newcastle upon Tyne, England, UK, 10-12 September 2014, pp. 423-432
summary	Research pavilions can serve as architectural scale demonstrations for the materialization of experimental forms and structures. Pavilions seek to prove and change methods of design and construction mechanisms in order to achieve desires such as material efficiency, novel spatial qualities and performative needs. The case of the ICD/ITKE Research Pavilion 2013-14 highlights the use of fiber composites in order to achieve a core-less filament winding modular system from bio-inspired lightweight structures through robotic fabrication. This paper describes the multi-disciplinary design and construction process of this pavilion that created a structure of out 36 unique components.
wos	WOS:000361384700042
keywords	Bio-inspired; fiber composites; multi-disciplinary design; robotic fabrication; modular system construction
series	eCAADe
email
last changed	2022/06/07 07:52

_id	8d4d
id	8d4d
authors	Leymarie F, Derix C, Miranda P, Coates P, Calderon C
year	2008
title	Medial Representations for driving the Architectural Creative Process
source	International Architecture Symposium, Barcelona, April 2008
summary	Medial representations of shape provide a powerful framework for the analysis and genesis of architectural forms,layouts, landscapes, cityscapes. In this paper we explore their potential use in driving the architectural creative process for 2D and 3D applications. We consider both the aspects of (i) the analysis of exisiting architectural layouts, and (ii) the genesis of novel ones. The archetypal medial representation of shape is the “medial axis” of Harry Blum (circa 1960). Boundary elements, the outline samples of the objects of interest, are used as the source of a wavefront propagation, for which the quenching points constitute axial symmetries. In 2D layout applications the resulting medial axis (MA) takes the form of a graph which unites geometry and topology of the objects and the field they occupy in one single framework. In the following we first survey the topic of shape representation via medial structures and consider their specific use in architectural analysis and genesis. We then report of early works in extending such ideas for novel applications relevant to architecture.
keywords	medial axis, spatial representation, user perception, occupancy
series	book
type	normal paper
email
last changed	2012/09/20 22:05

_id	a606
authors	Leão de Amorim, Arivaldo and Pereira, Gilberto Corso
year	2001
title	ATELIÊ COOPERATIVO DE SIMULAÇÃO DIGITAL EM ARQUITETURA E URBANISMO (Colaborative Studio for Architecture and Urbanism Digital Simulation)
source	SIGraDi biobio2001 - [Proceedings of the 5th Iberoamerican Congress of Digital Graphics / ISBN 956-7813-12-4] Concepcion (Chile) 21-23 november 2001, pp. 124-126
summary	Cooperative Atelier of Digital Simulation is a teaching proposal in that information technologies will be used intensively in the process of architectural design, particularly computer technologies for habitat simulation. In the first learning group, a experimental one - that should begin in the semester 2001.2, the computer will be used as an instrument for modeling, information management (spatial or not), making presentations, evaluation of alternatives and taking decisions, as well as for communication between the students’ teams and teachers of FAUFBA and, of other institutions that come to be integrating the project. The computer technologies could stand for the development of cooperative works. This paper synthesizes the proposal of creation of an optional discipline for students of Architecture and Urbanism.
series	SIGRADI
email
last changed	2016/03/10 09:54

_id	sigradi2006_p018d
id	sigradi2006_p018d
authors	Leão de Amorim, Arivaldo; Nogueira, Fabiano de Souza and Groetelaars, Natalie Johanna
year	2006
title	Em busca de uma Metodologia para Atualização cartográfica com tecnologias alternativas: um estudo de caso [Metodologyc search for a cartographic actualization with alternative technologies: A case study]
source	SIGraDi 2006 - [Proceedings of the 10th Iberoamerican Congress of Digital Graphics] Santiago de Chile - Chile 21-23 November 2006, pp. 368-372
summary	This paper presents an experiment using digital photogrammetry for the restitution of urban forms, using precise and low cost techniques, an alternative solution for the cartographic actualization of cities. The technique uses digital cameras (non-metric), with resolution compatible with the precision and scale required for the products. This process simplifies the acquisition of the photos, that can be taken by different places: in the ground, in the top of high buildings or by small airplanes or ultralights, in opposition of the traditional image acquisition method, done by costly aerial photogrammetric flights, realized by specialized companies.
series	SIGRADI
email
last changed	2016/03/10 09:54

_id	sigradi2007_af17
id	sigradi2007_af17
authors	León-Trujillo, Iván
year	2007
title	Design of products elaborated with laminar materials and textiles. From 3D-CAD models to pattern‘s documentation [Diseño de productos elaborados con textiles y laminares - Del 3D-CAD a la documentación de patrones bidimensionales]
source	SIGraDi 2007 - [Proceedings of the 11th Iberoamerican Congress of Digital Graphics] México D.F. - México 23-25 October 2007, pp. 315-321
summary	This paper expose a way in which we are educating our students in industrial design in Venezuela, particularly at the time when they deal with the design of products with textiles. In one hand, the elaboration of patterns from digital-CAD models is shown. Where stages of exploration in product development of complex articles, the process of “trial and error” has been practically eliminated with the use of a software-CAD. And in the other hand, the documentation of these patterns exhibit that this is not just a drawing of their designs, it will be a way to change the work system in our Small and Medium Industries.
series	SIGRADI
email
last changed	2016/03/10 09:54

_id	ecaade2023_296
id	ecaade2023_296
authors	Lharchi, Ayoub, Tamke, Martin, Nicholas, Paul, Eppinger, Carl, Sonne, Konrad, Valipour Goudarzi, Hasti, Rossi, Gabriella and Ramsgaard Thomsen, Mette
year	2023
title	Sensing and Augmenting for Adaptive Assembly Strategies
doi	https://doi.org/10.52842/conf.ecaade.2023.2.269
source	Dokonal, W, Hirschberg, U and Wurzer, G (eds.), Digital Design Reconsidered - Proceedings of the 41st Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2023) - Volume 2, Graz, 20-22 September 2023, pp. 269–276
summary	This paper introduces an innovative integrated approach to design, simulate, and test assembly strategies that adapt to tolerances and geometric variations. Traditional Design for Assembly (DfA) methods, while effective for well-known materials and predetermined design parameters, exhibit limitations in addressing unknown parameters and unpredictable material behavior. Our research employs techniques such as 3D scanning, laser projection, and early 1:1 prototyping to develop a flexible adaptive assembly model, accommodating last-minute structural and site condition changes. We demonstrate our novel workflow through the assembly and installation of a large-scale demonstrator at the AEDES gallery in Berlin, consisting of 24 variable-size 3D printed panels attached to a brick wall. By creating an initial assembly model using early detailing and a preliminary assembly sequence, we maximized the number of adaptable design parameters. An agent-based model was utilized to identify wall connection locations based on site constraints and fastener accessibility. Upon completing panel production, we used industrial laser projectors to compare digital files to actual pieces and 3D scanning to acquire accurate panel connection positions. This information enabled the regeneration of connection points with precise angles and dimensions and informed the final assembly sequence. On-site laser projection facilitated the efficient assembly of the structure. Our approach paves the way for more accurate and adaptable construction methods in complex architectural projects.
keywords	assembly information modeling, 3d scanning, laser projection, design for assembly, material behavior
series	eCAADe
email
last changed	2023/12/10 10:49

_id	2005_523
id	2005_523
authors	Li, Andrew I-Kang
year	2005
title	Thoughts on a Designer-friendly Shape Grammar Interpreter
doi	https://doi.org/10.52842/conf.ecaade.2005.523
source	Digital Design: The Quest for New Paradigms [23nd eCAADe Conference Proceedings / ISBN 0-9541183-3-2] Lisbon (Portugal) 21-24 September 2005, pp. 523-528
summary	Discussions of shape grammar interpreters overlook a fundamental issue: the model of the designer’s work. Such a model would provide guidance for developing an interpreter with an appropriate interface. In this paper, I first propose a model in which the designer’s work is to create and test generative specifications of languages of designs. I call this model designercentered generative design. Then, I examine the characteristics of shape grammar and how they support or impede this model of work. Finally, I discuss the implications for the design of an appropriate shape grammar interpreter. These provide guidelines for implementing such an interpreter for testing.
keywords	Shape Grammar; Interpreter
series	eCAADe
email
last changed	2022/06/07 07:59

_id	ecaade2009_118
id	ecaade2009_118
authors	Li, Andrew I-kang; Chen, Liang; Wang, Yang; Chau, Hau Hing
year	2009
title	Editing Shapes in a Prototype Two- and Three-dimensional Shape Grammar Environment
doi	https://doi.org/10.52842/conf.ecaade.2009.243
source	Computation: The New Realm of Architectural Design [27th eCAADe Conference Proceedings / ISBN 978-0-9541183-8-9] Istanbul (Turkey) 16-19 September 2009, pp. 243-250
summary	Recently we developed a prototype general shape grammar system, called Grammar Environment (Li et al. 2009). It differs from other systems in that it aims to support designers who design with shape grammars. One task of such a system is to support users in editing shapes. The guidelines that we followed in developing Grammar Environment suggested that the shape editing system should both be integrated into the system and be powerful as a drawing tool. This seemed to be contradictory. We decided to make two shape editors: one stronger on integration, the other on drawing power.
wos	WOS:000334282200030
keywords	Shape grammars, shape grammar interpreter, shape grammar environment
series	eCAADe
email
last changed	2022/06/07 07:59

_id	caadria2009_035
id	caadria2009_035
authors	Li, Andrew I-kang; Hau Hing Chau, Liang Chen, Yang Wang
year	2009
title	A Prototype System for developing two- and Three-Dimensional Shape Grammars
doi	https://doi.org/10.52842/conf.caadria.2009.717
source	Proceedings of the 14th International Conference on Computer Aided Architectural Design Research in Asia / Yunlin (Taiwan) 22-25 April 2009, pp. 717-726
summary	A number of researchers have developed shape grammar systems, with a variety of aims. These systems all help users (to varying degrees) to run grammars, but not to develop grammars. However, we believe that developing grammars is also work and needs to be supported. A system to do this would make it easier and more convenient for people using grammars to do design work. Following the generate-test model, we design and implement a prototype system that supports the user in editing grammars, testing grammars, and switching easily between the two types of activity. We emphasize the graphic nature of the task: the user is all the time working with graphic objects, namely shapes.
keywords	Shape grammar; interpreters; development; systems
series	CAADRIA
email
last changed	2022/06/07 07:59

_id	caadria2007_191
id	caadria2007_191
authors	Li, Biao
year	2007
title	A Generic House Design System: Expertise of Architectural Plan Generating
doi	https://doi.org/10.52842/conf.caadria.2007.x.u6h
source	CAADRIA 2007 [Proceedings of the 12th International Conference on Computer Aided Architectural Design Research in Asia] Nanjing (China) 19-21 April 2007
summary	This paper presents the process and decision of producing software named “Gen_house” that generates high quality sketches of architectural design tasks. The result of a successful project combining research, development and education in both Europe and Asia is achieved in order to ease the practice demand of considering multiple aspects within a design process. The software employs principles and methods of self- organization, agent based solutions and natural sciences, which brings them to the field of architectural design.
series	CAADRIA
email
last changed	2022/06/07 07:50

_id	caadria2023_246
id	caadria2023_246
authors	Li, Chenxiao, Bao, Ding Wen, Yan, Xin, Wu, Renhu and He, Chenming
year	2023
title	A Nature-Inspired Experimental Method for Re-Generating Porous Architectural Systems Based on Environmentally Data-Driven Performance
doi	https://doi.org/10.52842/conf.caadria.2023.1.271
source	Immanuel Koh, Dagmar Reinhardt, Mohammed Makki, Mona Khakhar, Nic Bao (eds.), HUMAN-CENTRIC - Proceedings of the 28th CAADRIA Conference, Ahmedabad, 18-24 March 2023, pp. 271–280
summary	Weathering scenery, as one of the most representative time-consuming natural features, is associated with many characteristics through aspects of specialized morphology, porosity, adaptability, and regenerative ability. Because of its unique porous structure and majestic, randomly three-dimensional composition, it has inspired lots of creations in industrial design, art crafts, and graphic design fields. But in architectural generative design, very limited projects are related to weathering. However, in recent decades, the advancements in computer-aided design tools have made it possible to implement rigorous computational methods in complex geometrical systems. This research tries to learn from the weathering evolution and apply the characteristics in the pursuit of enriching nature-inspired architecture. The experiments will focus on one specific weathering behavior, using wind-blown particles as weathering agents, and introduce an experimental method of generating the performance-based porosity architectural system responding to environmental agents’ effects. Computational Fluid Dynamics (CFD), Bi-Directional Evolutionary Structural Optimization (BESO), and Swarm Intelligence are employed to negotiate between surface, structure, and environmental space. This study of the porosity architectural system is concerned not only with discovering new possibilities for intricate and complex nature-inspired architectural forms, but also with negotiating and considering humans and nature as equal decision-makers.
keywords	Porosity, Topology Optimization, Bi-directional Evolutionary Structural Optimization (BESO), Swarm Intelligence, Computational Fluid Dynamics (CFD), Nature-inspired Form-Finding
series	CAADRIA
email
last changed	2023/06/15 23:14

_id	acadia22_90
id	acadia22_90
authors	Li, Chenxiao; Yuan, Mingyang; Han, Zilong; Faircloth, Billie; Anderson, Jeffrey S.; King, Nathan; Stuart-Smith, Robert
year	2022
title	Smart Branching
source	ACADIA 2022: Hybrids and Haecceities [Proceedings of the 42nd Annual Conference of the Association of Computer Aided Design in Architecture (ACADIA) ISBN 979-8-9860805-8-1]. University of Pennsylvania Stuart Weitzman School of Design. 27-29 October 2022. edited by M. Akbarzadeh, D. Aviv, H. Jamelle, and R. Stuart-Smith. 90-97.
summary	Through the design and fabrication of a 1.3m-high physical prototype sampled from our facade proposal, we developed a relatively automated project pipeline. It aims to achieve the generative and evolutionary design and a non-planar clay deposition method for tubular branching components.
series	ACADIA
type	paper
email
last changed	2024/02/06 14:00

_id	caadria2021_081
id	caadria2021_081
authors	Li, Danrui, Huang, Rong and Wu, Yihao
year	2021
title	Sensitivity Analysis of Pedestrian Simulation on Train station platforms
doi	https://doi.org/10.52842/conf.caadria.2021.2.529
source	A. Globa, J. van Ameijde, A. Fingrut, N. Kim, T.T.S. Lo (eds.), PROJECTIONS - Proceedings of the 26th CAADRIA Conference - Volume 2, The Chinese University of Hong Kong and Online, Hong Kong, 29 March - 1 April 2021, pp. 529-538
summary	As the concerns for pedestrian safety in station design are growing, multi-agent simulation becomes more widely used nowadays. While the difference between inputs in regard to their impacts on simulation outputs needs further research, previous studies fail to provide a global analysis of it in complex environments with limited computation resources. Therefore, regression-based SRC and revised Morris Method are employed in a sensitivity analysis of train station platform simulations. Results show that preference for escalators and alighting rate are influential parameters to all three concerned outputs while the standard deviation of walking speed is negligible. Given that most simulation users have limited time and resources, this paper provides a list of parameters that deserve the time and effort to calibrate together with a factor fixing method that can be applied in similar scenarios. In this way, simulation users can lower the uncertainty of train station simulations more efficiently.
keywords	Sensitivity analysis; Train station; Pedestrian; Simulation; Morris Method
series	CAADRIA
email
last changed	2022/06/07 07:52

_id	ecaade2013_132
id	ecaade2013_132
authors	Li, Di; Knight, Michael and Brown, Andre
year	2013
title	A Parametric Recreation of Traditional Chinese Architecture
doi	https://doi.org/10.52842/conf.ecaade.2013.2.697
source	Stouffs, Rudi and Sariyildiz, Sevil (eds.), Computation and Performance – Proceedings of the 31st eCAADe Conference – Volume 2, Faculty of Architecture, Delft University of Technology, Delft, The Netherlands, 18-20 September 2013, pp. 697-703
summary	This paper presents the current state of progress investigating the possibility of modelling traditional Chinese architecture using parametrics based on the two rule books. This builds on the work of producing systematic analysis on both rule books and contributing knowledge from extant buildings. The case study target is the floor plan described in Ying Zao Fa Shi. Discussion and future works are suggested at the end.
wos	WOS:000340643600072
keywords	Parametric modelling, traditional Chinese architecture, Ying Zao Fa Shi, Kung-ch’eng tso-fa tse-le, floor plan.
series	eCAADe
email
last changed	2022/06/07 07:52

_id	3d97
authors	Li, H. and Love, P.E.D.
year	1998
title	Design concept as a model for modelling design process and its knowledge
source	The Int. Journal of Construction IT 6(2), pp. 87-103
summary	The strategy of decomposing a design problem into subproblems is commonly used in engineering design. One difficulty in applying this strategy to computer-based design systems is the assembly of subproblem solutions to construct a whole solution. Despite its advantages, this design strategy suffers two major problems. First, as constraints are ill defined and implicitly exist among design objects, it is very difficult to articulate and represent design constraints in computable forms. Second, as design subproblems are designated separately in computer-based design systems, the inherent relationships among subproblems are not considered in contriving these subproblems. As a result, recomposing subproblem solutions is hard to do. This paper presents a model for modelling design processes and the knowledge involved. The model is called ‘design concept’, which represents empirical interconnections of design attributes and intraconnections of design subproblems. Topological relations are represented using decomposition trees. The advantages and disadvantages of integratively using decomposition trees and design concepts in facilitating conceptual design are discussed
series	journal paper
last changed	2003/05/15 21:45

_id	caadria2024_442
id	caadria2024_442
authors	Li, Jia-Rong, Chang, Teng-Wen, Chang, Ching-Chih, Huang, Hsin-Yi, Hong, Cheng-Chun and Chang, Ya-Chen
year	2024
title	CocoBot: Developing a Consent Communication Tool Based on Co-Evolutionary Model
doi	https://doi.org/10.52842/conf.caadria.2024.2.049
source	Nicole Gardner, Christiane M. Herr, Likai Wang, Hirano Toshiki, Sumbul Ahmad Khan (eds.), ACCELERATED DESIGN - Proceedings of the 29th CAADRIA Conference, Singapore, 20-26 April 2024, Volume 2, pp. 49–58
summary	In architecture and interior design, consent communication is crucial for the collaboration between clients and designers. With clients often needing assistance articulating particular design requirements, this study introduces CocoBot (Collaborative Consensus Bot), which integrates artificial intelligence-generated content (AIGC) technology into the communication of the design collaboration. This tool facilitates collaborative evolution between clients and designers by transforming requirements into tangible images, enhancing communication efficiency and consensus formation. The co-evolutionary model is at the core of CocoBot, which stimulates interaction and consensus formation between clients and interior designers by extracting semantic information from the communication process and generating images. It utilizes visualization to mitigate linguistic ambiguity and subjectivity, facilitating consensus attainment. Through qualitative research and expert interviews, we validate the effectiveness of CocoBot in improving communication between clients and designers, particularly in addressing language uncertainties and ambiguities, ushering in a new collaborative mode for designers and clients.
keywords	co-evolutionary model, Artificial Intelligence Generated Content (AIGC), design communication, collaboration, visualization, consensus formation
series	CAADRIA
email
last changed	2024/11/17 22:05

_id	caadria2024_166
id	caadria2024_166
authors	Li, Jinmin, Luo, Yilu, Lu, Shuai, Zhang, Jingyun, Wang, Jun, Guo, Rizen and Wang, ShaoMing
year	2024
title	ChatDesign: Bootstrapping Generative Floor Plan Design With Pre-trained Large Language Models
doi	https://doi.org/10.52842/conf.caadria.2024.1.099
source	Nicole Gardner, Christiane M. Herr, Likai Wang, Hirano Toshiki, Sumbul Ahmad Khan (eds.), ACCELERATED DESIGN - Proceedings of the 29th CAADRIA Conference, Singapore, 20-26 April 2024, Volume 1, pp. 99–108
summary	Large language models (LLMs) have achieved remarkable success in various domains, revolutionizing tasks such as language translation, text generation, and question-answering. However, generating floor plan designs poses a unique challenge that demands the fulfilment of intricate spatial and relational constraints. In this paper, we propose ChatDesign, an innovative approach that leverages the power of pre-trained LLMs to generate floor plan designs from natural language descriptions, while incorporating iterative modifications based on user interaction. By processing user input text through a pre-trained LLM and utilizing a decoder, we can generate regression parameters and floor plans that are precisely tailored to satisfy the specific needs of the user. Our approach incorporates an iterative refinement process, optimizing the model output by considering the input text and previous results. Throughout these interactions, we employ many strategic techniques to ensure the generated design images align precisely with the user's requirements. The proposed approach is extensively evaluated through rigorous experiments, including user studies, demonstrating its feasibility and efficacy. The empirical results consistently demonstrate the superiority of our method over existing approaches, showcasing its ability to generate floor plans that rival those created by human designer. Our code will be available at https://github.com/THU-Kingmin/ChatDesign.
keywords	floor plan generation, large language models, user interactions, automatic design, deep learning, pre-train models
series	CAADRIA
email
last changed	2024/11/17 22:05

_id	caadria2023_253
id	caadria2023_253
authors	Li, Jinze and Tang, Peng
year	2023
title	Multisource Analysis of Big Data on Street Vitality Using GIS Mapping and Deep Learning: A Case Study of Ding Shu, China
doi	https://doi.org/10.52842/conf.caadria.2023.1.565
source	Immanuel Koh, Dagmar Reinhardt, Mohammed Makki, Mona Khakhar, Nic Bao (eds.), HUMAN-CENTRIC - Proceedings of the 28th CAADRIA Conference, Ahmedabad, 18-24 March 2023, pp. 565–574
summary	Urban vitality is the driving force behind sustainable urban development. As the most frequently used public space in cities, the enhancement of street vitality is of great significance for improving human-centred habitats. Based on multi-source big data, this study uses spatial and statistical analysis methods to explore the impact factors of street vitality. Through the quantitative evaluation of these factors, we propose corresponding strategies to enhance the vitality of the street. Firstly, the spatial elements of streets are extracted using deep learning algorithm based on the acquired street view images. Further, the impact factors of street vitality are demonstrated using statistical methods by combining multi-source data. We established an evaluation system based on the impact factors of street vitality, which can quantify and predict street vitality. In this way, we can propose vitality enhancement strategy for the street with lower vitality in a targeted approach. The feasibility of the process is demonstrated by using Ding Shu as an example. This study provides a basic framework for a people-centred approach to enhance street vitality based on big data. It also contributes to causal inference in urban problems.
keywords	Multi-source data, street vitality, deep learning, spatial analysis, statistical analysis, causal inference, people-centred city
series	CAADRIA
email
last changed	2023/06/15 23:14

_id	caadria2024_465
id	caadria2024_465
authors	Li, Jinze, Song, Zhehao, Wen, Jian, Cai, Chenyi and Tang, Peng
year	2024
title	Exploring Nonlinear Relationship Between Built Environment and Street Vitality Using Machine Learning: A Case Study of Ding Shu, China
doi	https://doi.org/10.52842/conf.caadria.2024.2.375
source	Nicole Gardner, Christiane M. Herr, Likai Wang, Hirano Toshiki, Sumbul Ahmad Khan (eds.), ACCELERATED DESIGN - Proceedings of the 29th CAADRIA Conference, Singapore, 20-26 April 2024, Volume 2, pp. 375–384
summary	Urban vitality serves as the linchpin for sustainable urban development. Being the most extensively utilized public space within cities, augmenting street vitality bears paramount importance in accelerating design in human-centric habitats. This study employs spatial analysis and machine learning methods to explore the potential nonlinear relationships and local threshold effects between the built environment (BE) and street vitality based on multi-source data. This investigation provides support for the quantitative assessment and optimization of street vitality. Initially, using collected street view images, street spatial elements are extracted through deep learning algorithms. Subsequently, integrating multiple data sources, machine learning methods are employed to quantify the impact and interactions of the built environment on street vitality. Illustrated with the case of Dingshu, the feasibility of this process is demonstrated. By examining the correlation and underlying mechanisms between the built environment and street vitality, this study aids decision-makers in leveraging technological means to expedite design processes and create human-centric cities.
keywords	Nonlinear Relationship, Built Environment, Street Vitality, GBDT-SHAP, Interaction Effect
series	CAADRIA
email
last changed	2024/11/17 22:05

_id	caadria2024_88
id	caadria2024_88
authors	Li, Jiongye and Stouffs, Rudi
year	2024
title	Convolutional Neural Network-Based Predictions of Potential Flash Flood Hotspots in Singapore: Insights and Strategic Interventions
doi	https://doi.org/10.52842/conf.caadria.2024.2.069
source	Nicole Gardner, Christiane M. Herr, Likai Wang, Hirano Toshiki, Sumbul Ahmad Khan (eds.), ACCELERATED DESIGN - Proceedings of the 29th CAADRIA Conference, Singapore, 20-26 April 2024, Volume 2, pp. 69–78
summary	Amid increasing urbanization, changing climate, and limited stormwater infrastructure, urban flooding is a global issue, and Singapore is no exception. Traditional identification of flood-prone areas in Singapore has relied on historical flash flood data. However, by applying the booming influx of big data across various domains, including geography, weather, and DEM data, and using the deep learning model, Convolutional Neural Network (CNN), this research proposes a method that can accurately and effectively predict flash flood spots in an urban environment. Specifically, datasets including elevation, slope, aspect, rainfall, canals, drainage, and land use are fed into the CNN model to predict the locations of flash floods. The model, with a testing accuracy of 0.962, generates a comprehensive flash flood assessment map identifying high-risk areas in Singapore. Contrary to the current flood-prone area identification, which classifies only 0.79% of the country as susceptible to flash floods based on historical events, our CNN model-based assessment indicates that 11.4% of the country is at high risk. These newly identified zones are predominantly located along the coastline and in low-lying watershed outlets. Additionally, we propose corresponding stormwater infrastructure enhancements to mitigate flash flooding in these locations.
keywords	flash floods, flood prediction, convolutional neural network, geospatial data, flash flood assessment map, stormwater management measures
series	CAADRIA
email
last changed	2024/11/17 22:05

For more results click below: